New AI apps on the app hub including full documentation and a software trial

SECO has announced its latest release of AI applications, with seven new solutions launched over the past month. To ensure operational stability and efficiency, every application undergoes a rigorous validation process within the company's hardware ecosystem, delivering a seamless path for integration and deployment. This update also introduces a major platform enhancement: a 'Deploy' button that provides users instant access to a personal 90-day trial of the Clea instance.

To support this new hands-on workflow, every application is now fully documented in the recently launched SECO Developer Centre, supplying comprehensive deployment instructions, input/output specifications, and step-by-step testing guides.

The new solutions span a broad array of use cases, with seven applications addressing requirements that range from industrial quality control and predictive analytics to on-device conversational AI. These turnkey software assets empower client teams to redirect their development efforts toward what truly differentiates their products, while offloading the foundational complexities of AI implementation to SECO.

The new application release includes:

• Llama – Local Chatbot with Intel OpenVINO: An advanced, locally-run conversational AI that leverages Meta's powerful Llama model, optimised with OpenVINO for high performance on edge devices.
• Sensor Forecast – Smart Building (NeuralProphet): A time-series forecasting model designed to predict sensor data patterns in smart buildings, enabling proactive energy management and maintenance.
• Face ID + Edge Impulse: A facial recognition application developed in partnership with Edge Impulse, providing a streamlined experience for developers familiar with the popular edge ML platform.
• Scene Text Detection – High Accuracy and Light Model: Two new versions of an OCR application that
• detect and transcribe text from real-world images. The high-accuracy model is excellent for precision tasks, while the light model is optimised for speed on resource-constrained devices.
• PCB Defect Detection: A specialised computer vision model for manufacturing, designed to identify defects on PCBs during quality control inspections automatically.
• YAMNet – Training Experience: An application built around the YAMNet audio event classification model, providing a framework for users to easily train the system to recognise new, custom sounds for their specific use case.

"We are enabling our clients to build powerful, custom AI/ML pipelines without getting bogged down by the underlying technological complexities," says Fausto Di Segni, head of IoT and AI at SECO. "By integrating the Application Hub, the instant Clea trial, and the comprehensive documentation in our Developer Centre, we are giving anyone building a smart product the power to not only test our AI, but to apply it to their own data streams."

The App Hub's strategy is built on a dual promise of flexibility and reliability. Developers can confidently deploy these new applications on their preferred platforms from Intel, Qualcomm, NXP, AMD, Rockchip, and MediaTek, knowing each solution is covered by SECO's enterprise Long-Term Support. The upcoming turnkey deployment capabilities of the Clea framework will further simplify this ecosystem.